TAU2
Measured May 29, 2026Source
Score
0.94
Models9 0 
DeepSeek V4 Pro (Reasoning, High Effort)
DeepSeekDeepSeekChina
A high-effort reasoning model from the DeepSeek V4 series, optimized for complex problem-solving and deep analytical tasks. It likely employs extended thinking or chain-of-thought processes to tackle challenging queries in coding, mathematics, and logic.
CodingReasoning
Input / 1M tokens
$0.435Output / 1M tokens
$0.87Output tokens/s
48.59First-token seconds
1.35sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 29, 2026Source
Score
0.42
Lcr
Measured May 29, 2026Source
Score
0.65
Ifbench
Measured May 29, 2026Source
Score
0.71
Scicode
Measured May 29, 2026Source
Score
0.46
Hle
Measured May 29, 2026Source
Score
0.34
Gpqa
Measured May 29, 2026Source
Score
0.91
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
43.2
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
49.8
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server